\begin{thebibliography}{10}

\bibitem{Arl:2007:phd}
Sylvain Arlot.
\newblock {\em Resampling and Model Selection}.
\newblock PhD thesis, University Paris-Sud 11, December 2007.
\newblock oai:tel.archives-ouvertes.fr:tel-00198803\_v1.

\bibitem{Arl:2008a}
Sylvain Arlot.
\newblock {$V$}-fold cross-validation improved: {$V$}-fold penalization,
  February 2008.
\newblock arXiv:0802.0566v2.

\bibitem{Arl:2009:RP}
Sylvain Arlot.
\newblock Model selection by resampling penalization.
\newblock {\em Electron. J. Stat.}, 3:557--624 (electronic), 2009.

\bibitem{Arl_Mas:2009:pente}
Sylvain Arlot and Pascal Massart.
\newblock Data-driven calibration of penalties for least-squares regression.
\newblock {\em J. Mach. Learn. Res.}, 10:245--279 (electronic), 2009.

\bibitem{Aud:2004:PMA908}
Jean-Yves Audibert.
\newblock Classification under polynomial entropy and margin assumptions and
  randomized estimators.
\newblock Preprint, Laboratoire de Probabilites et Modeles Aleatoires, 2004.

\bibitem{Aud_Tsy:2007}
Jean-Yves Audibert and Alexandre~B. Tsybakov.
\newblock Fast learning rates for plug-in classifiers.
\newblock {\em Ann. Statist.}, 35(2):608--633, 2007.

\bibitem{Bar_Bir_Mas:1999}
Andrew Barron, Lucien Birg{\'e}, and Pascal Massart.
\newblock Risk bounds for model selection via penalization.
\newblock {\em Probab. Theory Related Fields}, 113(3):301--413, 1999.

\bibitem{Bar_Bou_Men:2005}
Peter~L. Bartlett, Olivier Bousquet, and Shahar Mendelson.
\newblock Local {R}ademacher complexities.
\newblock {\em Annals of Statistics}, 33(4):1497--1537, 2005.

\bibitem{Bar_Jor_McA:2006}
Peter~L.\ Bartlett, Michael~I.\ Jordan, and Jon~D.\ McAuliffe.
\newblock Convexity, classification, and risk bounds.
\newblock {\em Journal of the American Statistical Association},
  101(473):138--156, 2006.

\bibitem{Bar_Men_Phi:2004}
Peter~L. Bartlett, Shahar Mendelson, and Petra Philips.
\newblock Local complexities for empirical risk minimization.
\newblock In {\em Learning theory}, volume 3120 of {\em Lecture Notes in
  Comput. Sci.}, pages 270--284. Springer, Berlin, 2004.

\bibitem{Bir_Mas:1998}
Lucien Birg{\'e} and Pascal Massart.
\newblock Minimum contrast estimators on sieves: exponential bounds and rates
  of convergence.
\newblock {\em Bernoulli}, 4(3):329--375, 1998.

\bibitem{Bla_Lug_Vay:2003}
Gilles Blanchard, G{\'a}bor Lugosi, and Nicolas Vayatis.
\newblock On the rate of convergence of regularized boosting classifiers.
\newblock {\em J. Mach. Learn. Res.}, 4(5):861--894, 2004.

\bibitem{Bla_Mas:2006}
Gilles Blanchard and Pascal Massart.
\newblock Discussion: ``{L}ocal {R}ademacher complexities and oracle
  inequalities in risk minimization'' [{A}nn. {S}tatist. {\bf 34} (2006), no.
  6, 2593--2656] by {V}. {K}oltchinskii.
\newblock {\em Ann. Statist.}, 34(6):2664--2671, 2006.

\bibitem{Dev_Lug:1995}
Luc Devroye and G{\'a}bor Lugosi.
\newblock Lower bounds in pattern recognition and learning.
\newblock {\em Pattern Recognition}, 28(7):1011--1018, 1995.

\bibitem{Efr:1983}
Bradley Efron.
\newblock Estimating the error rate of a prediction rule: improvement on
  cross-validation.
\newblock {\em J. Amer. Statist. Assoc.}, 78(382):316--331, 1983.

\bibitem{Kol:2006}
Vladimir Koltchinskii.
\newblock Local {R}ademacher complexities and oracle inequalities in risk
  minimization.
\newblock {\em Ann. Statist.}, 34(6):2593--2656, 2006.

\bibitem{Lec:2007c}
Guillaume Lecu{\'e}.
\newblock Simultaneous adaptation to the margin and to complexity in
  classification.
\newblock {\em Ann. Statist.}, 35(4):1698--1721, 2007.

\bibitem{Lec:2007b}
Guillaume Lecu{\'e}.
\newblock Suboptimality of penalized empirical risk minimization in
  classification.
\newblock In {\em COLT 2007}, volume 4539 of {\em Lecture Notes in Artificial
  Intelligence}. Springer, Berlin, 2007.

\bibitem{Lug:2002}
G{\'a}bor Lugosi.
\newblock Pattern classification and learning theory.
\newblock In {\em Principles of nonparametric learning (Udine, 2001)}, volume
  434 of {\em CISM Courses and Lectures}, pages 1--56. Springer, Vienna, 2002.

\bibitem{Lug_Weg:2004}
G{\'a}bor Lugosi and Marten Wegkamp.
\newblock Complexity regularization via localized random penalties.
\newblock {\em Ann. Statist.}, 32(4):1679--1697, 2004.

\bibitem{Mam_Tsy:1999}
Enno Mammen and Alexandre~B. Tsybakov.
\newblock Smooth discrimination analysis.
\newblock {\em Ann. Statist.}, 27(6):1808--1829, 1999.

\bibitem{Mas:2003:St-Flour}
Pascal Massart.
\newblock {\em Concentration inequalities and model selection}, volume 1896 of
  {\em Lecture Notes in Mathematics}.
\newblock Springer, Berlin, 2007.
\newblock Lectures from the 33rd Summer School on Probability Theory held in
  Saint-Flour, July 6--23, 2003.

\bibitem{Mas_Ned:2003}
Pascal Massart and {\'E}lodie N{\'e}d{\'e}lec.
\newblock Risk bounds for statistical learning.
\newblock {\em Ann. Statist.}, 34(5):2326--2366, 2006.

\bibitem{Tsy:2004}
Alexandre~B. Tsybakov.
\newblock Optimal aggregation of classifiers in statistical learning.
\newblock {\em Ann. Statist.}, 32(1):135--166, 2004.

\bibitem{Tsy_vdG:2005}
Alexandre~B. Tsybakov and Sara~A. van~de Geer.
\newblock Square root penalty: adaptation to the margin in classification and
  in edge estimation.
\newblock {\em Ann. Statist.}, 33(3):1203--1224, 2005.

\bibitem{Vap:1998}
Vladimir~N. Vapnik.
\newblock {\em Statistical learning theory}.
\newblock John Wiley \& Sons Inc., New York, 1998.

\bibitem{vc-ucrfep-71}
Vladimir~N. Vapnik and A.~Y. Chervonenkis.
\newblock On the uniform convergence of relative frequencies of events to their
  probabilities.
\newblock {\em Theory of Probability and its Applications}, 16(2):264--280,
  1971.

\end{thebibliography}